geometallurgy 0.4.11__py3-none-any.whl → 0.4.13__py3-none-any.whl

elphick/geomet/config/__init__.py

@@ -1 +1 @@
-from .config_read import read_yaml
+from .config_read import read_yaml

elphick/geomet/config/config_read.py

@@ -1,39 +1,39 @@
-import logging
-from typing import Dict
-
-import yaml
-
-
-def read_yaml(file_path):
-    with open(file_path, "r") as f:
-        d_config: Dict = yaml.safe_load(f)
-        if 'MC' != list(d_config.keys())[0]:
-            msg: str = f'config file {file_path} is not a MassComposition config file - no MC key'
-            logging.error(msg)
-            raise KeyError(msg)
-        return d_config['MC']
-
-
-def read_flowsheet_yaml(file_path):
-    with open(file_path, "r") as f:
-        d_config: Dict = yaml.safe_load(f)
-        if 'FLOWSHEET' != list(d_config.keys())[0]:
-            msg: str = f'config file {file_path} is not a Flowsheet config file - no FLOWSHEET key'
-            logging.error(msg)
-            raise KeyError(msg)
-        return d_config['FLOWSHEET']
-
-
-def get_column_config(config_dict: dict, var_map: dict, config_key: str = 'range') -> dict:
-    res: dict = {}
-    # populate from the config
-    # var_map only includes mass-composition columns, no supplementary. vars are keys, cols are values
-    composition_cols = [v for k, v in var_map.items() if k not in ['mass_wet', 'mass_dry', 'moisture']]
-
-    for k, v in config_dict['vars'].items():
-        if k == 'composition':
-            for col in composition_cols:
-                res[col] = v[config_key]
-        elif k in list(var_map.keys()) and v.get(config_key):
-            res[var_map[k]] = v[config_key]
-    return res
+import logging
+from typing import Dict
+
+import yaml
+
+
+def read_yaml(file_path):
+    with open(file_path, "r") as f:
+        d_config: Dict = yaml.safe_load(f)
+        if 'MC' != list(d_config.keys())[0]:
+            msg: str = f'config file {file_path} is not a MassComposition config file - no MC key'
+            logging.error(msg)
+            raise KeyError(msg)
+        return d_config['MC']
+
+
+def read_flowsheet_yaml(file_path):
+    with open(file_path, "r") as f:
+        d_config: Dict = yaml.safe_load(f)
+        if 'FLOWSHEET' != list(d_config.keys())[0]:
+            msg: str = f'config file {file_path} is not a Flowsheet config file - no FLOWSHEET key'
+            logging.error(msg)
+            raise KeyError(msg)
+        return d_config['FLOWSHEET']
+
+
+def get_column_config(config_dict: dict, var_map: dict, config_key: str = 'range') -> dict:
+    res: dict = {}
+    # populate from the config
+    # var_map only includes mass-composition columns, no supplementary. vars are keys, cols are values
+    composition_cols = [v for k, v in var_map.items() if k not in ['mass_wet', 'mass_dry', 'moisture']]
+
+    for k, v in config_dict['vars'].items():
+        if k == 'composition':
+            for col in composition_cols:
+                res[col] = v[config_key]
+        elif k in list(var_map.keys()) and v.get(config_key):
+            res[var_map[k]] = v[config_key]
+    return res

elphick/geomet/config/flowsheet_example_partition.yaml

@@ -1,31 +1,31 @@
-FLOWSHEET:
-  flowsheet:
-    name: Flowsheet
-  streams:  # graph edges
-    Feed:
-      name: Feed
-      node_in: feed
-      node_out: screen
-    Coarse:
-      name: Coarse
-      node_in: screen
-      node_out: lump
-    Fine:
-      name: Fine
-      node_in: screen
-      node_out: fines
-  operations:  # graph nodes
-    feed:
-      name: feed
-    screen:
-      name: screen
-      type: PartitionOperation
-      partition:
-        module: elphick.geomet.utils.partition
-        function: napier_munn_size_1mm
-        partition_stream: Lump  # the stream that the partition model defines
-        args: null  # e.g. d50, ep if not defined in the (partial) function
-    lump:
-      name: lump
-    fines:
-      name: fines
+FLOWSHEET:
+  flowsheet:
+    name: Flowsheet
+  streams:  # graph edges
+    Feed:
+      name: Feed
+      node_in: feed
+      node_out: screen
+    Coarse:
+      name: Coarse
+      node_in: screen
+      node_out: lump
+    Fine:
+      name: Fine
+      node_in: screen
+      node_out: fines
+  operations:  # graph nodes
+    feed:
+      name: feed
+    screen:
+      name: screen
+      type: PartitionOperation
+      partition:
+        module: elphick.geomet.utils.partition
+        function: napier_munn_size_1mm
+        partition_stream: Lump  # the stream that the partition model defines
+        args: null  # e.g. d50, ep if not defined in the (partial) function
+    lump:
+      name: lump
+    fines:
+      name: fines

elphick/geomet/config/flowsheet_example_simple.yaml

@@ -1,25 +1,25 @@
-FLOWSHEET:
-  flowsheet:
-    name: Flowsheet
-  streams:  # graph edges
-    Feed:
-      name: Feed
-      node_in: feed
-      node_out: screen
-    Coarse:
-      name: Coarse
-      node_in: screen
-      node_out: lump
-    Fine:
-      name: Fine
-      node_in: screen
-      node_out: fines
-  operations:  # graph nodes
-    feed:
-      name: feed
-    screen:
-      name: screen
-    lump:
-      name: lump
-    fines:
-      name: fines
+FLOWSHEET:
+  flowsheet:
+    name: Flowsheet
+  streams:  # graph edges
+    Feed:
+      name: Feed
+      node_in: feed
+      node_out: screen
+    Coarse:
+      name: Coarse
+      node_in: screen
+      node_out: lump
+    Fine:
+      name: Fine
+      node_in: screen
+      node_out: fines
+  operations:  # graph nodes
+    feed:
+      name: feed
+    screen:
+      name: screen
+    lump:
+      name: lump
+    fines:
+      name: fines

elphick/geomet/config/mc_config.yml

@@ -1,35 +1,35 @@
-MC:
-  vars:
-    mass_wet:
-      default_name: 'mass_wet'
-      search_regex: '(mass_wet)|(wet_mass)|(wmt)'  # case in-sensitive regex
-      format: '%.0f'  # cannot use %d, use %.
-      range: [0.0, .inf] # the range of valid values
-    mass_dry:
-      default_name: 'mass_dry'
-      search_regex: '(mass_dry)|(dry_mass)|(dmt)'
-      format: '%.0f'
-      range: [ 0.0, .inf]
-    moisture:
-      default_name: 'h2o'
-      search_regex: '(h2o)|(moisture)|(moist)'
-      format: '%.1f'
-      range: [0.0, 100.0]
-    composition:
-      ignore: ['Y']  # ignore anything in this list when detecting chemistry components
-      format: '%.2f'
-      range: [0.0, 100.0]
-    fe:
-      range: [0.0, 69.97]  # hematite
-  intervals:
-    closed: left
-    suffixes:
-      - [from, to]
-      - [retained, passing]
-      - [sink, float]
-      - [lo, hi]
-  comparisons:
-    recovery: 'rec'
-    difference: 'diff'
-    divide: 'ur'
-
+MC:
+  vars:
+    mass_wet:
+      default_name: 'mass_wet'
+      search_regex: '(mass_wet)|(wet_mass)|(wmt)'  # case in-sensitive regex
+      format: '%.0f'  # cannot use %d, use %.
+      range: [0.0, .inf] # the range of valid values
+    mass_dry:
+      default_name: 'mass_dry'
+      search_regex: '(mass_dry)|(dry_mass)|(dmt)'
+      format: '%.0f'
+      range: [ 0.0, .inf]
+    moisture:
+      default_name: 'h2o'
+      search_regex: '(h2o)|(moisture)|(moist)'
+      format: '%.1f'
+      range: [0.0, 100.0]
+    composition:
+      ignore: ['Y']  # ignore anything in this list when detecting chemistry components
+      format: '%.2f'
+      range: [0.0, 100.0]
+    fe:
+      range: [0.0, 69.97]  # hematite
+  intervals:
+    closed: left
+    suffixes:
+      - [from, to]
+      - [retained, passing]
+      - [sink, float]
+      - [lo, hi]
+  comparisons:
+    recovery: 'rec'
+    difference: 'diff'
+    divide: 'ur'
+

elphick/geomet/data/downloader.py

@@ -1,39 +1,39 @@
-import webbrowser
-from pathlib import Path
-from typing import Dict
-
-import pandas as pd
-import platformdirs
-import pooch
-from pooch import Unzip, Pooch
-
-
-class Downloader:
-    def __init__(self):
-        """Instantiate a Downloader
-        """
-
-        self.register: pd.DataFrame = pd.read_csv(Path(__file__).parent / 'register.csv', index_col=False)
-
-        self.dataset_hashes: Dict = self.register[['target', 'target_sha256']].set_index('target').to_dict()[
-            'target_sha256']
-
-        self.downloader: Pooch = pooch.create(path=Path(platformdirs.user_cache_dir('mass_composition', 'elphick')),
-                                              base_url="https://github.com/elphick/mass-composition/raw/main/docs"
-                                                       "/source/_static/",
-                                              version=None,
-                                              version_dev=None,
-                                              registry={**self.dataset_hashes})
-
-    def load_data(self, datafile: str = 'size_by_assay.zip', show_report: bool = False) -> pd.DataFrame:
-        """
-        Load the 231575341_size_by_assay data as a pandas.DataFrame.
-        """
-        if datafile not in self.dataset_hashes.keys():
-            raise KeyError(f"The file {datafile} is not in the registry containing: {self.dataset_hashes.keys()}")
-
-        fnames = self.downloader.fetch(datafile, processor=Unzip())
-        if show_report:
-            webbrowser.open(str(Path(fnames[0]).with_suffix('.html')))
-        data = pd.read_csv(Path(fnames[0]).with_suffix('.csv'))
-        return data
+import webbrowser
+from pathlib import Path
+from typing import Dict
+
+import pandas as pd
+import platformdirs
+import pooch
+from pooch import Unzip, Pooch
+
+
+class Downloader:
+    def __init__(self):
+        """Instantiate a Downloader
+        """
+
+        self.register: pd.DataFrame = pd.read_csv(Path(__file__).parent / 'register.csv', index_col=False)
+
+        self.dataset_hashes: Dict = self.register[['target', 'target_sha256']].set_index('target').to_dict()[
+            'target_sha256']
+
+        self.downloader: Pooch = pooch.create(path=Path(platformdirs.user_cache_dir('mass_composition', 'elphick')),
+                                              base_url="https://github.com/elphick/mass-composition/raw/main/docs"
+                                                       "/source/_static/",
+                                              version=None,
+                                              version_dev=None,
+                                              registry={**self.dataset_hashes})
+
+    def load_data(self, datafile: str = 'size_by_assay.zip', show_report: bool = False) -> pd.DataFrame:
+        """
+        Load the 231575341_size_by_assay data as a pandas.DataFrame.
+        """
+        if datafile not in self.dataset_hashes.keys():
+            raise KeyError(f"The file {datafile} is not in the registry containing: {self.dataset_hashes.keys()}")
+
+        fnames = self.downloader.fetch(datafile, processor=Unzip())
+        if show_report:
+            webbrowser.open(str(Path(fnames[0]).with_suffix('.html')))
+        data = pd.read_csv(Path(fnames[0]).with_suffix('.csv'))
+        return data

elphick/geomet/data/register.csv

@@ -1,12 +1,12 @@
-,dataset,datafile,bytes,metadata,report,archive,datafile_md5,target_filepath,target,target_sha256
-0,A072391_assay,..\..\datasets\A072391_assay\A072391_assay.csv,32891149,True,True,True,957309836cb748525974aa690c5f919a,..\..\datasets\A072391_assay\A072391_assay.zip,A072391_assay.zip,b669840cc90aaa2d615986cdcf4ef5f97ec7352032597adc93440b154159d41f
-1,A072391_collars,..\..\datasets\A072391_collars\A072391_collars.csv,765470,True,True,True,597f5fe444270fe4409814b002b6e5cd,..\..\datasets\A072391_collars\A072391_collars.zip,A072391_collars.zip,9c01345766dc39462327c26604bddbd02db38f76118fe092bc90407e15bb5d09
-2,A072391_geo,..\..\datasets\A072391_geo\A072391_geo.csv,23544608,True,True,True,cdd8aed2841c73f3c203b995e099b590,..\..\datasets\A072391_geo\A072391_geo.zip,A072391_geo.zip,cf687584cc891fa084a45432e82747b7ef581eb21fe54f885f0b4c4f342c1641
-3,A072391_met,..\..\datasets\A072391_met\A072391_met.csv,412184,True,True,True,d2ac41f41ab7ba56f8239d63dba8a906,..\..\datasets\A072391_met\A072391_met.zip,A072391_met.zip,f4f84eeb4826755410d9979771a7e4f96afa2333586be85b775f179ece9c7bdf
-4,A072391_wireline,..\..\datasets\A072391_wireline\A072391_wireline.csv,4904606,True,True,True,6c810d264e83fe9c25576a53ebe8ff07,..\..\datasets\A072391_wireline\A072391_wireline.zip,A072391_wireline.zip,d3a566ec8806277a6c4e7a594d8e39f9e71c634947f9001766a03d32683e4baf
-5,demo_data,..\..\datasets\demo_data\demo_data.csv,284,True,True,True,746da032cebd545d165bdc5f3c9fb625,..\..\datasets\demo_data\demo_data.zip,demo_data.zip,0e294393e3980da04ba18f56a3a0a8f9fac2fa8f066f773846e23a6a9de89d8e
-6,iron_ore_sample_A072391,..\..\datasets\iron_ore_sample_A072391\iron_ore_sample_A072391.csv,10923,True,True,True,8403fb2acbc37e98738486ba5f49fa7d,..\..\datasets\iron_ore_sample_A072391\iron_ore_sample_A072391.zip,iron_ore_sample_A072391.zip,698b6ae7dacded385fcddf39070d8dfead0b769cc0127363ad9fec03f38d61b0
-7,iron_ore_sample_xyz_A072391,..\..\datasets\iron_ore_sample_xyz_A072391\iron_ore_sample_xyz_A072391.csv,14496,True,True,True,4ea605c41b073a304514a8c5e1d9cca3,..\..\datasets\iron_ore_sample_xyz_A072391\iron_ore_sample_xyz_A072391.zip,iron_ore_sample_xyz_A072391.zip,37dd3872d4da12b0a145f7f52b43c2541da44b1ef21826757dc3616aa372766d
-8,nordic_iron_ore_sink_float,..\..\datasets\nordic_iron_ore_sink_float\nordic_iron_ore_sink_float.csv,698,True,True,True,9ff12a4195620133a93ddc34c026745e,..\..\datasets\nordic_iron_ore_sink_float\nordic_iron_ore_sink_float.zip,nordic_iron_ore_sink_float.zip,f796f2b07b55466e2392cfe4b10d50f12de8ed9c39e231f216773a41d925faa1
-9,size_by_assay,..\..\datasets\size_by_assay\size_by_assay.csv,249,True,True,True,3ea813789ad8efb1b9d4cbb7d47f00a4,..\..\datasets\size_by_assay\size_by_assay.zip,size_by_assay.zip,28010532f3da6d76fa32aa2ae8c4521c83f9864f8f0972949c931a49ad982d7c
-10,size_distribution,..\..\datasets\size_distribution\size_distribution.csv,565,True,True,True,bd183c8240cceda4c9690746a69ce729,..\..\datasets\size_distribution\size_distribution.zip,size_distribution.zip,cd996c940010e859a16dbf508a9928fdbd04c9278c5eb1131873444db7382766
+,dataset,datafile,bytes,metadata,report,archive,datafile_md5,target_filepath,target,target_sha256
+0,A072391_assay,..\..\datasets\A072391_assay\A072391_assay.csv,32891149,True,True,True,957309836cb748525974aa690c5f919a,..\..\datasets\A072391_assay\A072391_assay.zip,A072391_assay.zip,b669840cc90aaa2d615986cdcf4ef5f97ec7352032597adc93440b154159d41f
+1,A072391_collars,..\..\datasets\A072391_collars\A072391_collars.csv,765470,True,True,True,597f5fe444270fe4409814b002b6e5cd,..\..\datasets\A072391_collars\A072391_collars.zip,A072391_collars.zip,9c01345766dc39462327c26604bddbd02db38f76118fe092bc90407e15bb5d09
+2,A072391_geo,..\..\datasets\A072391_geo\A072391_geo.csv,23544608,True,True,True,cdd8aed2841c73f3c203b995e099b590,..\..\datasets\A072391_geo\A072391_geo.zip,A072391_geo.zip,cf687584cc891fa084a45432e82747b7ef581eb21fe54f885f0b4c4f342c1641
+3,A072391_met,..\..\datasets\A072391_met\A072391_met.csv,412184,True,True,True,d2ac41f41ab7ba56f8239d63dba8a906,..\..\datasets\A072391_met\A072391_met.zip,A072391_met.zip,f4f84eeb4826755410d9979771a7e4f96afa2333586be85b775f179ece9c7bdf
+4,A072391_wireline,..\..\datasets\A072391_wireline\A072391_wireline.csv,4904606,True,True,True,6c810d264e83fe9c25576a53ebe8ff07,..\..\datasets\A072391_wireline\A072391_wireline.zip,A072391_wireline.zip,d3a566ec8806277a6c4e7a594d8e39f9e71c634947f9001766a03d32683e4baf
+5,demo_data,..\..\datasets\demo_data\demo_data.csv,284,True,True,True,746da032cebd545d165bdc5f3c9fb625,..\..\datasets\demo_data\demo_data.zip,demo_data.zip,0e294393e3980da04ba18f56a3a0a8f9fac2fa8f066f773846e23a6a9de89d8e
+6,iron_ore_sample_A072391,..\..\datasets\iron_ore_sample_A072391\iron_ore_sample_A072391.csv,10923,True,True,True,8403fb2acbc37e98738486ba5f49fa7d,..\..\datasets\iron_ore_sample_A072391\iron_ore_sample_A072391.zip,iron_ore_sample_A072391.zip,698b6ae7dacded385fcddf39070d8dfead0b769cc0127363ad9fec03f38d61b0
+7,iron_ore_sample_xyz_A072391,..\..\datasets\iron_ore_sample_xyz_A072391\iron_ore_sample_xyz_A072391.csv,14496,True,True,True,4ea605c41b073a304514a8c5e1d9cca3,..\..\datasets\iron_ore_sample_xyz_A072391\iron_ore_sample_xyz_A072391.zip,iron_ore_sample_xyz_A072391.zip,37dd3872d4da12b0a145f7f52b43c2541da44b1ef21826757dc3616aa372766d
+8,nordic_iron_ore_sink_float,..\..\datasets\nordic_iron_ore_sink_float\nordic_iron_ore_sink_float.csv,698,True,True,True,9ff12a4195620133a93ddc34c026745e,..\..\datasets\nordic_iron_ore_sink_float\nordic_iron_ore_sink_float.zip,nordic_iron_ore_sink_float.zip,f796f2b07b55466e2392cfe4b10d50f12de8ed9c39e231f216773a41d925faa1
+9,size_by_assay,..\..\datasets\size_by_assay\size_by_assay.csv,249,True,True,True,3ea813789ad8efb1b9d4cbb7d47f00a4,..\..\datasets\size_by_assay\size_by_assay.zip,size_by_assay.zip,28010532f3da6d76fa32aa2ae8c4521c83f9864f8f0972949c931a49ad982d7c
+10,size_distribution,..\..\datasets\size_distribution\size_distribution.csv,565,True,True,True,bd183c8240cceda4c9690746a69ce729,..\..\datasets\size_distribution\size_distribution.zip,size_distribution.zip,cd996c940010e859a16dbf508a9928fdbd04c9278c5eb1131873444db7382766

elphick/geomet/datasets/__init__.py

@@ -1,2 +1,2 @@
-from .downloader import Downloader
-from .datasets import *
+from .downloader import Downloader
+from .datasets import *

elphick/geomet/datasets/datasets.py

@@ -1,47 +1,47 @@
-from elphick.geomet.datasets import Downloader
-import pandas as pd
-
-
-def load_a072391_assay(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='A072391_assay.zip', show_report=show_report)
-
-
-def load_a072391_collars(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='A072391_collars.zip', show_report=show_report)
-
-
-def load_a072391_geo(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='A072391_geo.zip', show_report=show_report)
-
-
-def load_a072391_met(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='A072391_met.zip', show_report=show_report)
-
-
-def load_a072391_wireline(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='A072391_wireline.zip', show_report=show_report)
-
-
-def load_demo_data(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='demo_data.zip', show_report=show_report)
-
-
-def load_iron_ore_sample_a072391(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='iron_ore_sample_A072391.zip', show_report=show_report)
-
-
-def load_iron_ore_sample_xyz_a072391(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='iron_ore_sample_xyz_A072391.zip', show_report=show_report)
-
-
-def load_nordic_iron_ore_sink_float(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='nordic_iron_ore_sink_float.zip', show_report=show_report)
-
-
-def load_size_by_assay(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='size_by_assay.zip', show_report=show_report)
-
-
-def load_size_distribution(show_report: bool = False) -> pd.DataFrame:
-    return Downloader().load_data(datafile='size_distribution.zip', show_report=show_report)
-
+from elphick.geomet.datasets import Downloader
+import pandas as pd
+
+
+def load_a072391_assay(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='A072391_assay.zip', show_report=show_report)
+
+
+def load_a072391_collars(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='A072391_collars.zip', show_report=show_report)
+
+
+def load_a072391_geo(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='A072391_geo.zip', show_report=show_report)
+
+
+def load_a072391_met(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='A072391_met.zip', show_report=show_report)
+
+
+def load_a072391_wireline(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='A072391_wireline.zip', show_report=show_report)
+
+
+def load_demo_data(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='demo_data.zip', show_report=show_report)
+
+
+def load_iron_ore_sample_a072391(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='iron_ore_sample_A072391.zip', show_report=show_report)
+
+
+def load_iron_ore_sample_xyz_a072391(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='iron_ore_sample_xyz_A072391.zip', show_report=show_report)
+
+
+def load_nordic_iron_ore_sink_float(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='nordic_iron_ore_sink_float.zip', show_report=show_report)
+
+
+def load_size_by_assay(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='size_by_assay.zip', show_report=show_report)
+
+
+def load_size_distribution(show_report: bool = False) -> pd.DataFrame:
+    return Downloader().load_data(datafile='size_distribution.zip', show_report=show_report)
+

elphick/geomet/datasets/downloader.py

@@ -1,40 +1,40 @@
-import webbrowser
-from pathlib import Path
-from typing import Dict
-
-import pandas as pd
-import platformdirs
-import pooch
-from pooch import Unzip, Pooch
-
-
-class Downloader:
-    def __init__(self):
-        """Instantiate a Downloader
-        """
-
-        self.register: pd.DataFrame = pd.read_csv(Path(__file__).parent / 'register.csv', index_col=False)
-
-        self.dataset_hashes: Dict = self.register[['target', 'target_sha256']].set_index('target').to_dict()[
-            'target_sha256']
-
-        self.downloader: Pooch = pooch.create(path=Path(platformdirs.user_cache_dir('mass_composition', 'elphick')),
-                                              base_url="https://github.com/elphick/mass-composition/raw/main/docs"
-                                                       "/source/_static/",
-                                              version=None,
-                                              version_dev=None,
-                                              registry={**self.dataset_hashes})
-
-    def load_data(self, datafile: str = 'size_by_assay.zip', show_report: bool = False) -> pd.DataFrame:
-        """
-        Load the 231575341_size_by_assay data as a pandas.DataFrame.
-        """
-        if datafile not in self.dataset_hashes.keys():
-            raise KeyError(f"The file {datafile} is not in the registry containing: {self.dataset_hashes.keys()}")
-
-        fnames = self.downloader.fetch(datafile, processor=Unzip())
-        if show_report:
-            webbrowser.open(str(Path(fnames[0]).with_suffix('.html')))
-        data = pd.read_csv(Path(fnames[0]).with_suffix('.csv'))
-        return data
-
+import webbrowser
+from pathlib import Path
+from typing import Dict
+
+import pandas as pd
+import platformdirs
+import pooch
+from pooch import Unzip, Pooch
+
+
+class Downloader:
+    def __init__(self):
+        """Instantiate a Downloader
+        """
+
+        self.register: pd.DataFrame = pd.read_csv(Path(__file__).parent / 'register.csv', index_col=False)
+
+        self.dataset_hashes: Dict = self.register[['target', 'target_sha256']].set_index('target').to_dict()[
+            'target_sha256']
+
+        self.downloader: Pooch = pooch.create(path=Path(platformdirs.user_cache_dir('mass_composition', 'elphick')),
+                                              base_url="https://github.com/elphick/mass-composition/raw/main/docs"
+                                                       "/source/_static/",
+                                              version=None,
+                                              version_dev=None,
+                                              registry={**self.dataset_hashes})
+
+    def load_data(self, datafile: str = 'size_by_assay.zip', show_report: bool = False) -> pd.DataFrame:
+        """
+        Load the 231575341_size_by_assay data as a pandas.DataFrame.
+        """
+        if datafile not in self.dataset_hashes.keys():
+            raise KeyError(f"The file {datafile} is not in the registry containing: {self.dataset_hashes.keys()}")
+
+        fnames = self.downloader.fetch(datafile, processor=Unzip())
+        if show_report:
+            webbrowser.open(str(Path(fnames[0]).with_suffix('.html')))
+        data = pd.read_csv(Path(fnames[0]).with_suffix('.csv'))
+        return data
+

elphick/geomet/datasets/register.csv

@@ -1,12 +1,12 @@
-,dataset,datafile,bytes,metadata,report,archive,datafile_md5,target_filepath,target,target_sha256
-0,A072391_assay,..\..\datasets\A072391_assay\A072391_assay.csv,32891149,True,True,True,957309836cb748525974aa690c5f919a,..\..\datasets\A072391_assay\A072391_assay.zip,A072391_assay.zip,b669840cc90aaa2d615986cdcf4ef5f97ec7352032597adc93440b154159d41f
-1,A072391_collars,..\..\datasets\A072391_collars\A072391_collars.csv,765470,True,True,True,597f5fe444270fe4409814b002b6e5cd,..\..\datasets\A072391_collars\A072391_collars.zip,A072391_collars.zip,9c01345766dc39462327c26604bddbd02db38f76118fe092bc90407e15bb5d09
-2,A072391_geo,..\..\datasets\A072391_geo\A072391_geo.csv,23544608,True,True,True,cdd8aed2841c73f3c203b995e099b590,..\..\datasets\A072391_geo\A072391_geo.zip,A072391_geo.zip,cf687584cc891fa084a45432e82747b7ef581eb21fe54f885f0b4c4f342c1641
-3,A072391_met,..\..\datasets\A072391_met\A072391_met.csv,412184,True,True,True,d2ac41f41ab7ba56f8239d63dba8a906,..\..\datasets\A072391_met\A072391_met.zip,A072391_met.zip,f4f84eeb4826755410d9979771a7e4f96afa2333586be85b775f179ece9c7bdf
-4,A072391_wireline,..\..\datasets\A072391_wireline\A072391_wireline.csv,4904606,True,True,True,6c810d264e83fe9c25576a53ebe8ff07,..\..\datasets\A072391_wireline\A072391_wireline.zip,A072391_wireline.zip,d3a566ec8806277a6c4e7a594d8e39f9e71c634947f9001766a03d32683e4baf
-5,demo_data,..\..\datasets\demo_data\demo_data.csv,284,True,True,True,746da032cebd545d165bdc5f3c9fb625,..\..\datasets\demo_data\demo_data.zip,demo_data.zip,0e294393e3980da04ba18f56a3a0a8f9fac2fa8f066f773846e23a6a9de89d8e
-6,iron_ore_sample_A072391,..\..\datasets\iron_ore_sample_A072391\iron_ore_sample_A072391.csv,10923,True,True,True,8403fb2acbc37e98738486ba5f49fa7d,..\..\datasets\iron_ore_sample_A072391\iron_ore_sample_A072391.zip,iron_ore_sample_A072391.zip,698b6ae7dacded385fcddf39070d8dfead0b769cc0127363ad9fec03f38d61b0
-7,iron_ore_sample_xyz_A072391,..\..\datasets\iron_ore_sample_xyz_A072391\iron_ore_sample_xyz_A072391.csv,14496,True,True,True,4ea605c41b073a304514a8c5e1d9cca3,..\..\datasets\iron_ore_sample_xyz_A072391\iron_ore_sample_xyz_A072391.zip,iron_ore_sample_xyz_A072391.zip,37dd3872d4da12b0a145f7f52b43c2541da44b1ef21826757dc3616aa372766d
-8,nordic_iron_ore_sink_float,..\..\datasets\nordic_iron_ore_sink_float\nordic_iron_ore_sink_float.csv,698,True,True,True,9ff12a4195620133a93ddc34c026745e,..\..\datasets\nordic_iron_ore_sink_float\nordic_iron_ore_sink_float.zip,nordic_iron_ore_sink_float.zip,f796f2b07b55466e2392cfe4b10d50f12de8ed9c39e231f216773a41d925faa1
-9,size_by_assay,..\..\datasets\size_by_assay\size_by_assay.csv,249,True,True,True,3ea813789ad8efb1b9d4cbb7d47f00a4,..\..\datasets\size_by_assay\size_by_assay.zip,size_by_assay.zip,28010532f3da6d76fa32aa2ae8c4521c83f9864f8f0972949c931a49ad982d7c
-10,size_distribution,..\..\datasets\size_distribution\size_distribution.csv,565,True,True,True,bd183c8240cceda4c9690746a69ce729,..\..\datasets\size_distribution\size_distribution.zip,size_distribution.zip,cd996c940010e859a16dbf508a9928fdbd04c9278c5eb1131873444db7382766
+,dataset,datafile,bytes,metadata,report,archive,datafile_md5,target_filepath,target,target_sha256
+0,A072391_assay,..\..\datasets\A072391_assay\A072391_assay.csv,32891149,True,True,True,957309836cb748525974aa690c5f919a,..\..\datasets\A072391_assay\A072391_assay.zip,A072391_assay.zip,b669840cc90aaa2d615986cdcf4ef5f97ec7352032597adc93440b154159d41f
+1,A072391_collars,..\..\datasets\A072391_collars\A072391_collars.csv,765470,True,True,True,597f5fe444270fe4409814b002b6e5cd,..\..\datasets\A072391_collars\A072391_collars.zip,A072391_collars.zip,9c01345766dc39462327c26604bddbd02db38f76118fe092bc90407e15bb5d09
+2,A072391_geo,..\..\datasets\A072391_geo\A072391_geo.csv,23544608,True,True,True,cdd8aed2841c73f3c203b995e099b590,..\..\datasets\A072391_geo\A072391_geo.zip,A072391_geo.zip,cf687584cc891fa084a45432e82747b7ef581eb21fe54f885f0b4c4f342c1641
+3,A072391_met,..\..\datasets\A072391_met\A072391_met.csv,412184,True,True,True,d2ac41f41ab7ba56f8239d63dba8a906,..\..\datasets\A072391_met\A072391_met.zip,A072391_met.zip,f4f84eeb4826755410d9979771a7e4f96afa2333586be85b775f179ece9c7bdf
+4,A072391_wireline,..\..\datasets\A072391_wireline\A072391_wireline.csv,4904606,True,True,True,6c810d264e83fe9c25576a53ebe8ff07,..\..\datasets\A072391_wireline\A072391_wireline.zip,A072391_wireline.zip,d3a566ec8806277a6c4e7a594d8e39f9e71c634947f9001766a03d32683e4baf
+5,demo_data,..\..\datasets\demo_data\demo_data.csv,284,True,True,True,746da032cebd545d165bdc5f3c9fb625,..\..\datasets\demo_data\demo_data.zip,demo_data.zip,0e294393e3980da04ba18f56a3a0a8f9fac2fa8f066f773846e23a6a9de89d8e
+6,iron_ore_sample_A072391,..\..\datasets\iron_ore_sample_A072391\iron_ore_sample_A072391.csv,10923,True,True,True,8403fb2acbc37e98738486ba5f49fa7d,..\..\datasets\iron_ore_sample_A072391\iron_ore_sample_A072391.zip,iron_ore_sample_A072391.zip,698b6ae7dacded385fcddf39070d8dfead0b769cc0127363ad9fec03f38d61b0
+7,iron_ore_sample_xyz_A072391,..\..\datasets\iron_ore_sample_xyz_A072391\iron_ore_sample_xyz_A072391.csv,14496,True,True,True,4ea605c41b073a304514a8c5e1d9cca3,..\..\datasets\iron_ore_sample_xyz_A072391\iron_ore_sample_xyz_A072391.zip,iron_ore_sample_xyz_A072391.zip,37dd3872d4da12b0a145f7f52b43c2541da44b1ef21826757dc3616aa372766d
+8,nordic_iron_ore_sink_float,..\..\datasets\nordic_iron_ore_sink_float\nordic_iron_ore_sink_float.csv,698,True,True,True,9ff12a4195620133a93ddc34c026745e,..\..\datasets\nordic_iron_ore_sink_float\nordic_iron_ore_sink_float.zip,nordic_iron_ore_sink_float.zip,f796f2b07b55466e2392cfe4b10d50f12de8ed9c39e231f216773a41d925faa1
+9,size_by_assay,..\..\datasets\size_by_assay\size_by_assay.csv,249,True,True,True,3ea813789ad8efb1b9d4cbb7d47f00a4,..\..\datasets\size_by_assay\size_by_assay.zip,size_by_assay.zip,28010532f3da6d76fa32aa2ae8c4521c83f9864f8f0972949c931a49ad982d7c
+10,size_distribution,..\..\datasets\size_distribution\size_distribution.csv,565,True,True,True,bd183c8240cceda4c9690746a69ce729,..\..\datasets\size_distribution\size_distribution.zip,size_distribution.zip,cd996c940010e859a16dbf508a9928fdbd04c9278c5eb1131873444db7382766